Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to emotional expressions and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kháu
    -0.82
     pend
    -0.76
     المعيارى
    -0.73
    ^(@)
    -0.73
     Feu
    -0.71
    +#+#
    -0.70
    #+#
    -0.70
    SequentialGroup
    -0.70
    こち
    -0.69
    љено
    -0.69
    POSITIVE LOGITS
    ’
    1.14
    .’”
    1.14
    、“
    1.13
    “
    1.07
    ’,
    1.03
    ’”
    1.02
    ’.
    1.01
    ’;
    1.00
    ,’”
    1.00
     “
    0.99
    Act Density 0.373%

    No Known Activations